diff options
Diffstat (limited to 'r_qtl')
| -rw-r--r-- | r_qtl/r_qtl2.py | 82 | ||||
| -rw-r--r-- | r_qtl/r_qtl2_qc.py | 2 |
2 files changed, 66 insertions, 18 deletions
diff --git a/r_qtl/r_qtl2.py b/r_qtl/r_qtl2.py index 9da4081..0ef487f 100644 --- a/r_qtl/r_qtl2.py +++ b/r_qtl/r_qtl2.py @@ -16,7 +16,11 @@ from r_qtl.exceptions import InvalidFormat, MissingFileException FILE_TYPES = ( "geno", "founder_geno", "pheno", "covar", "phenocovar", "gmap", "pmap", - "phenose") + "phenose", "phenonum") + +__CONTROL_FILE_ERROR_MESSAGE__ = ( + "The zipped bundle that was provided does not contain a valid control file " + "in either JSON or YAML format.") def __special_file__(filename): @@ -72,6 +76,8 @@ def transpose_csv( def __read_by_line__(_path): with open(_path, "r", encoding="utf8") as infile: for line in infile: + if line.startswith("#"): + continue yield line transposed_data= (f"{linejoinerfn(items)}\n" for items in zip(*( @@ -112,7 +118,7 @@ def __control_data_from_zipfile__(zfile: ZipFile) -> dict: or filename.endswith(".json")))) num_files = len(files) if num_files == 0: - raise InvalidFormat("Expected a json or yaml control file.") + raise InvalidFormat(__CONTROL_FILE_ERROR_MESSAGE__) if num_files > 1: raise InvalidFormat("Found more than one possible control file.") @@ -129,7 +135,6 @@ def __control_data_from_zipfile__(zfile: ZipFile) -> dict: else yaml.safe_load(zfile.read(files[0]))) } - def __control_data_from_dirpath__(dirpath: Path): """Load control data from a given directory path.""" files = tuple(path for path in dirpath.iterdir() @@ -137,7 +142,7 @@ def __control_data_from_dirpath__(dirpath: Path): and (path.suffix in (".yaml", ".json")))) num_files = len(files) if num_files == 0: - raise InvalidFormat("Expected a json or yaml control file.") + raise InvalidFormat(__CONTROL_FILE_ERROR_MESSAGE__) if num_files > 1: raise InvalidFormat("Found more than one possible control file.") @@ -182,7 +187,7 @@ def control_data(control_src: Union[Path, ZipFile]) -> dict: r_qtl.exceptions.InvalidFormat """ def __cleanup__(cdata): - return { + _cdata = { **cdata, **dict((filetype, ([cdata[filetype]] if isinstance(cdata[filetype], str) @@ -190,6 +195,14 @@ def control_data(control_src: Union[Path, ZipFile]) -> dict: ) for filetype in (typ for typ in cdata.keys() if typ in FILE_TYPES)) } + if "na.string" in _cdata:# handle common error in file. + _cdata = { + **cdata, + "na.strings": list(set( + _cdata["na.string"] + _cdata["na.strings"])) + } + + return _cdata if isinstance(control_src, ZipFile): return __cleanup__(__control_data_from_zipfile__(control_src)) @@ -200,8 +213,8 @@ def control_data(control_src: Union[Path, ZipFile]) -> dict: if control_src.is_dir(): return __cleanup__(__control_data_from_dirpath__(control_src)) raise InvalidFormat( - "Expects either a zipfile.ZipFile object or a pathlib.Path object " - "pointing to a directory containing the R/qtl2 bundle.") + "Expects either a zipped bundle of files or a path-like object " + "pointing to the zipped R/qtl2 bundle.") def replace_na_strings(cdata, val): @@ -398,22 +411,19 @@ def file_data(zfile: ZipFile, try: if isinstance(cdata[member_key], list): - for row in (line for lines in + yield from (line for lines in (file_data( zfile, member_key, {**cdata, member_key: innerfile}, process_value, process_transposed_value) for innerfile in cdata[member_key]) - for line in lines): - yield row + for line in lines) return if not cdata.get(f"{member_key}_transposed", False): - for row in with_non_transposed(zfile, member_key, cdata, process_value): - yield row + yield from with_non_transposed(zfile, member_key, cdata, process_value) return - for row in with_transposed( - zfile, member_key, cdata, process_transposed_value): - yield row + yield from with_transposed( + zfile, member_key, cdata, process_transposed_value) except KeyError as exc: raise MissingFileException(*exc.args) from exc @@ -464,8 +474,7 @@ def raw_file_data(zipfilepath: Union[str, Path], with (ZipFile(str(zipfilepath), "r") as zfile, zfile.open(memberfilename) as innerfile): wrappedfile = io.TextIOWrapper(innerfile) - for line in wrappedfile: - yield line + yield from wrappedfile def strip_comments(rawdata: Iterator[str], commentchar) -> Iterator[str]: """Remove comments from raw text.""" @@ -549,3 +558,42 @@ def load_samples(zipfilepath: Union[str, Path], pass return tuple(samples) + + + +def read_text_file(filepath: Union[str, Path]) -> Iterator[str]: + """Read the raw text from a text file.""" + with open(filepath, "r", encoding="utf8") as _file: + yield from _file + + +def read_csv_file(filepath: Union[str, Path], + separator: str = ",", + comment_char: str = "#") -> Iterator[tuple[str, ...]]: + """Read a file as a csv file. This does not process the N/A values.""" + for line in read_text_file(filepath): + if line.startswith(comment_char): + continue + yield tuple(field.strip() for field in line.split(separator)) + + +def read_csv_file_headers( + filepath: Union[str, Path], + transposed: bool, + separator: str = ",", + comment_char: str = "#" +) -> tuple[str, ...]: + """Read the 'true' headers of a CSV file.""" + headers = tuple() + for line in read_text_file(filepath): + if line.startswith(comment_char): + continue + + line = tuple(field.strip() for field in line.split(separator)) + if not transposed: + return line + + headers = headers + (line[0],) + continue + + return headers diff --git a/r_qtl/r_qtl2_qc.py b/r_qtl/r_qtl2_qc.py index 7b26b50..2d9e9a8 100644 --- a/r_qtl/r_qtl2_qc.py +++ b/r_qtl/r_qtl2_qc.py @@ -95,7 +95,7 @@ def missing_files(bundlesrc: Union[Path, ZipFile]) -> tuple[tuple[str, str], ... "pointing to a directory containing the R/qtl2 bundle.") -def validate_bundle(zfile: ZipFile): +def validate_bundle(zfile: Union[Path, ZipFile]): """Ensure the R/qtl2 bundle is valid.""" missing = missing_files(zfile) if len(missing) > 0: |